arXiv cs.LG
· Papers
What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry
arXiv:2607.13046v1 Announce Type: new Abstract: We develop a framework for the information discarded by machine learning models whose inputs carry a Lie group action. Given a representation $pi$ of a Lie group $G$ on a space $V$ and a learned function $fcolon V to mathbb{R}$, we define two objects measuring the sym